ClawHub
Back to skill

Security audit

git-essentials

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Git command reference skill, but users should treat destructive Git examples as actions that need explicit confirmation.

Install this as a Git reference skill, not as permission for automatic repository changes. Before allowing an agent to run commands from it, confirm the target repository, branch, remote, and whether commands like reset hard, clean, branch deletion, tag deletion, or force-with-lease could discard work or rewrite history.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger phrases are very broad and include generic terms like 'git', 'commit', 'push', and '版本控制', which can cause the skill to activate in contexts where the user did not explicitly request Git operational guidance. In an agentic environment, over-broad activation increases the chance of unsolicited or context-inappropriate command suggestions, including destructive Git operations elsewhere in the skill.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
### Q5: 如何撤销已推送的提交？

A: 已推送至共享分支的提交，使用 `git revert commit-hash` 生成反向提交再推送；仅在个人独占分支才可考虑 `git reset --hard` 后强制推送。

### Q6: 如何合并多个提交为一个？
Confidence
88% confidence
Finding
git reset --hard

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.